Introduction to AI

This repo holds the learning materials taught by Yuxiao (Rain) Luo and related to the undergraduate INFS course Advanced Data Analytics and AI.

Want to keep up with AI technology developments? Check out the weekly AI news digests:

• Weekly Digest of AI Events in 2025.

Course Description

This course explores artificial intelligence as a transformative tool in business, focusing on practical applications, strategic integration, and ethical considerations. Students will gain insight into AI’s foundational concepts, engage with industry-specific use cases, and analyze AI’s impact on organizational strategy. Through case studies, simulations, and expert talks, students will develop a managerial perspective on AI and learn to leverage AI as a source of competitive advantage.

Tentative Schedule

Please follow the official syllabus and find the coursework tab for each week. All Python code (IPython Notebook file) is included in this GitHub repo.

Prompting

• Awesome ChatGPT Prompts
• Learn Prompting
• Prompt Engineering Guide from DAIR.AI

Coding Demo

• Python Basics

  • Data Type and Structures
  • Intro to Analytics

• AI Analytics

  • Descriptive analytics
  • Diagnostic analytics
  • Supervised learning
  • Text mining 1
  • Text mining 2
  • Image mining 1
  • Image mining 2
  • Image mining 3 - video detection
  • Image mining 4 - customized model
  • Image mining 5 - realtime object
  • Resources:
    • Generative AI Data Scientist
    • LLM Token Estimator
    • Open-source LLM in Python: langchain-ollama
    • Open-source LLM in R: rollama
    • LLM in R: tidyllm

• AI Applications

  • Text-to-Speech (tts)
  • LLM (Google Gemini)

Git & GitHub Tutorials

• 00 Review of Command Line

• 01 Learning Git Basics

• 02 Setting Up Git

• 03 Creating a Syllabus File

• 04 Staging and Committing Changes

• 05 Pushing to GitHub

LLM System & APIs

Ollama

Ollama is a free, open-source tool that allows users to run large language models (LLMs) locally on their computers. Details can be found on their GitHub Page.

1. Download Ollama (Windows/macOS/Linux).
2. To use the LLMs in Ollama, you can use
   • ollama-python, the Python library for Ollama.
   • Or use Command Line program. Ex., Command Prompt for WindowsOS and Terminal for macOS.
3. Let's get started with the tutorial.
4. Please be aware of the security issues of ollama: read the article vulnerabilities in ollama

APIs

Here is the list of APIs used in the course. Since we only use free versions of these APIs, some may come with use limit. Please click into each link to obtain the API key for yourself (free account registration is needed).

• Alpha Vantage API: fetch news for LLM to do sentiment analysis from AlphaVantage, they provide free stock API service covering the majority of their datasets for up to 25 requests per day.
• Google Gemini API: call Gemini LLM API.

Agentic AI

Context Management

• 00 Context Window
• 01 Context Compaction
• 02 Context Editing
• 03 Prompt Caching

Agent Skills

Agent Skills provide an open, discoverable standard for extending AI agents with new capabilities. A skill packages instructions, scripts, and supporting resources into a structured format that agents can load to perform specific tasks.

At the core of each skill is a folder anchored by a SKILL.md file. This file defines metadata and step-by-step procedural guidance that instructs the agent how to execute a particular workflow. By standardizing how tasks are described and performed, skills enable reusable, consistent, and reliable task execution.

Skills give agents on-demand access to domain expertise and contextual knowledge, helping bridge capability gaps and support repeatable, auditable workflows across compatible platforms. Because the format is open and portable, skill creators can build capabilities once and deploy them across multiple agents—while preserving organizational knowledge in version-controlled, shareable packages.

• 00 What are agent skills
• 01 How to construct agent skills
• 02 Example skills - see what's possible

AI Agents (open- and closed-source)

OpenClaw

OpenClaw is an open-source personal AI assistant that runs on your own devices and integrates directly into messaging platforms like WhatsApp, Telegram, Slack, Discord, Teams, and more, so you can interact with it through the channels you already use. It operates locally and continuously, with voice support on macOS, iOS, and Android, plus a live Canvas interface you can control, while the Gateway serves only as the control plane behind the assistant. Setup is easiest through the terminal onboarding wizard (openclaw onboard), which walks you through configuring the gateway, channels, and skills, and it supports subscriptions like Anthropic Claude and OpenAI models for advanced capabilities.

1. Usecase 1 - Automated Quant Finance alpha model
2. Usecase 2 - PolyMarket trader agent

n8n

n8n is a closed-source workflow automation platform that enables the development of agentic AI systems. It supports the construction of AI agents and retrieval-augmented generation (RAG) pipelines through extensive, highly flexible integrations with a wide range of software tools.

1. Self-hosted AI Starter Kit.
2. Usecase 1 - Chat with a database using AI.
3. Usecase 2 - Automated competitor pricing monitor with Bright Data MCP & OpenAI
4. Usecase 3 - Generate funny AI videos with Sora 2 and auto-publish to TikTok

Google Opal

Google Opal is a no-code agentic AI platform for creating mini-AI apps. It connects AI models (like Gemini) with tools and prompts to automate tasks and create content without writing code. Users create visual workflows with steps like user input, generative AI, and outputs (which can go to Docs/Sheets), then publish them as shareable web apps for personal or collaborative use.

1. Tutorial 1 - A beginner's guide to to Google opal
2. Tutorial 2 - Official Guide from Google Labs

How to download Jupter Notebook File from this Github Repo

Click this instruction.

Markdown format

This README page is created with Markdown format, which is easy to learn here.